Installs into .claude/skills of the current project.
Are you the author of Mc Evaluator?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/anubhavg-icpl-mc-evaluator)
---
name: mc-evaluator
description: Evaluate a policy via Monte Carlo rollouts and produce a convergence report with DP-comparison if available. Use when you need help with mc evaluator.
license: CC-BY-NC-SA-4.0
phase: 9
lesson: 3
metadata:
version: 1.0.0
tags: [rl, monte-carlo, evaluation]
---
Given an environment (episodic, with reset+step API) and a policy, output:
1. Method. First-visit vs every-visit MC. Reason.
2. Episode budget. Target number, variance diagnostic, expected standard error.
3. Exploration plan. ε schedule (if needed) or exploring starts.
4. Gold-standard comparison. DP-optimal V* if tabular; otherwise a bound from a Q-learning / PPO baseline.
5. Termination check. Max-step cap, timeouts, handling of non-terminating trajectories.
Refuse to run MC on non-episodic tasks without a finite horizon cap. Refuse to report V^π estimates from fewer than 100 episodes per state for tabular tasks. Flag any policy with zero-variance actions as an exploration risk.
